[Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

vfork() is a kind of fork, not thread despite CLONE_VM

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index eba2c02..ae7a5a2 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -2787,7 +2787,7 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
     sigset_t sigmask;
 #endif
 
-    if (flags & CLONE_VM) {
+    if (!(flags & CLONE_VFORK) && (flags & CLONE_VM)) {
 #if defined(USE_NPTL)
         new_thread_info info;
         pthread_attr_t attr;
@@ -2856,8 +2856,8 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
 #endif
 #endif
     } else {
-        /* if no CLONE_VM, we consider it is a fork */
-        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2)) != 0)
+        /* we consider it is a fork or vfork */
+        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2 | CLONE_VFORK | CLONE_VM)) != 0)
             return -EINVAL;
         fork_start();
         ret = fork();
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Fix getgroups() syscall emulation

[Kirill A. Shutemov]

According to man page getgroups(2):

If size is zero, list is not modified, but the total number of
supplementary group IDs for the process is returned.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index ae7a5a2..9d8542d 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -5242,6 +5242,8 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
 
             grouplist = alloca(gidsetsize * sizeof(gid_t));
             ret = get_errno(getgroups(gidsetsize, grouplist));
+            if (gidsetsize == 0)
+                break;
             if (!is_error(ret)) {
                 target_grouplist = lock_user(VERIFY_WRITE, arg2, gidsetsize * 2, 0);
                 if (!target_grouplist)
@@ -5392,6 +5394,8 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
 
             grouplist = alloca(gidsetsize * sizeof(gid_t));
             ret = get_errno(getgroups(gidsetsize, grouplist));
+            if (gidsetsize == 0)
+                break;
             if (!is_error(ret)) {
                 target_grouplist = lock_user(VERIFY_WRITE, arg2, gidsetsize * 4, 0);
                 if (!target_grouplist) {
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Swap only altered elements of the grouplist

[Kirill A. Shutemov]

getgroups returns the number of supplementary group IDs is returned.
So it's unnessary to swap the entire array. It can dramatically speed up
the syscall: on recent Linux kernel NGROUPS_MAX=65536.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 9d8542d..8112a56 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -5248,7 +5248,7 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
                 target_grouplist = lock_user(VERIFY_WRITE, arg2, gidsetsize * 2, 0);
                 if (!target_grouplist)
                     goto efault;
-                for(i = 0;i < gidsetsize; i++)
+                for(i = 0;i < ret; i++)
                     target_grouplist[i] = tswap16(grouplist[i]);
                 unlock_user(target_grouplist, arg2, gidsetsize * 2);
             }
@@ -5402,7 +5402,7 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
                     ret = -TARGET_EFAULT;
                     goto fail;
                 }
-                for(i = 0;i < gidsetsize; i++)
+                for(i = 0;i < ret; i++)
                     target_grouplist[i] = tswap32(grouplist[i]);
                 unlock_user(target_grouplist, arg2, gidsetsize * 4);
             }
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Fix pread() and pwrite() syscall on ARM EABI

[Kirill A. Shutemov]

pread() and pwrite() have differences with arguments on ARM EABI and
OABI.

Please, see arch/arm/kernel/entry-common.S in Linux kernel source for
additional information.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |   12 ++++++++++++
 1 files changed, 12 insertions(+), 0 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 8112a56..88954eb 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -5042,12 +5042,24 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
 #endif
 #ifdef TARGET_NR_pread
     case TARGET_NR_pread:
+#ifdef TARGET_ARM
+        if (((CPUARMState *)cpu_env)->eabi)
+        {
+            arg4 = arg5;
+        }
+#endif
         if (!(p = lock_user(VERIFY_WRITE, arg2, arg3, 0)))
             goto efault;
         ret = get_errno(pread(arg1, p, arg3, arg4));
         unlock_user(p, arg2, ret);
         break;
     case TARGET_NR_pwrite:
+#ifdef TARGET_ARM
+        if (((CPUARMState *)cpu_env)->eabi)
+        {
+            arg4 = arg5;
+        }
+#endif
         if (!(p = lock_user(VERIFY_READ, arg2, arg3, 1)))
             goto efault;
         ret = get_errno(pwrite(arg1, p, arg3, arg4));
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Implement syscall fstatat64()

[Kirill A. Shutemov]

Move transformation of struct stat64 into the separate function and
implement fstatat64() using it.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |  136 ++++++++++++++++++++++++++++---------------------
 1 files changed, 78 insertions(+), 58 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 88954eb..863e319 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -3148,6 +3148,67 @@ static inline abi_long host_to_target_timespec(abi_ulong target_addr,
     return 0;
 }
 
+#ifdef TARGET_NR_stat64
+static inline abi_long host_to_target_stat64(void *cpu_env,
+					     abi_ulong target_addr,
+					     struct stat *host_st)
+{
+#ifdef TARGET_ARM
+	if (((CPUARMState *)cpu_env)->eabi) {
+		struct target_eabi_stat64 *target_st;
+
+		if (!lock_user_struct(VERIFY_WRITE, target_st, target_addr, 0))
+			return -TARGET_EFAULT;
+		memset(target_st, 0, sizeof(struct target_eabi_stat64));
+		__put_user(host_st->st_dev, &target_st->st_dev);
+		__put_user(host_st->st_ino, &target_st->st_ino);
+#ifdef TARGET_STAT64_HAS_BROKEN_ST_INO
+		__put_user(host_st->st_ino, &target_st->__st_ino);
+#endif
+		__put_user(host_st->st_mode, &target_st->st_mode);
+		__put_user(host_st->st_nlink, &target_st->st_nlink);
+		__put_user(host_st->st_uid, &target_st->st_uid);
+		__put_user(host_st->st_gid, &target_st->st_gid);
+		__put_user(host_st->st_rdev, &target_st->st_rdev);
+		__put_user(host_st->st_size, &target_st->st_size);
+		__put_user(host_st->st_blksize, &target_st->st_blksize);
+		__put_user(host_st->st_blocks, &target_st->st_blocks);
+		__put_user(host_st->st_atime, &target_st->target_st_atime);
+		__put_user(host_st->st_mtime, &target_st->target_st_mtime);
+		__put_user(host_st->st_ctime, &target_st->target_st_ctime);
+		unlock_user_struct(target_st, target_addr, 1);
+	} else
+#endif
+	{
+		struct target_stat64 *target_st;
+
+		if (!lock_user_struct(VERIFY_WRITE, target_st, target_addr, 0))
+			return -TARGET_EFAULT;
+		memset(target_st, 0, sizeof(struct target_stat64));
+		__put_user(host_st->st_dev, &target_st->st_dev);
+		__put_user(host_st->st_ino, &target_st->st_ino);
+#ifdef TARGET_STAT64_HAS_BROKEN_ST_INO
+		__put_user(host_st->st_ino, &target_st->__st_ino);
+#endif
+		__put_user(host_st->st_mode, &target_st->st_mode);
+		__put_user(host_st->st_nlink, &target_st->st_nlink);
+		__put_user(host_st->st_uid, &target_st->st_uid);
+		__put_user(host_st->st_gid, &target_st->st_gid);
+		__put_user(host_st->st_rdev, &target_st->st_rdev);
+		/* XXX: better use of kernel struct */
+		__put_user(host_st->st_size, &target_st->st_size);
+		__put_user(host_st->st_blksize, &target_st->st_blksize);
+		__put_user(host_st->st_blocks, &target_st->st_blocks);
+		__put_user(host_st->st_atime, &target_st->target_st_atime);
+		__put_user(host_st->st_mtime, &target_st->target_st_mtime);
+		__put_user(host_st->st_ctime, &target_st->target_st_ctime);
+		unlock_user_struct(target_st, target_addr, 1);
+	}
+
+	return 0;
+}
+#endif
+
 #if defined(USE_NPTL)
 /* ??? Using host futex calls even when target atomic operations
    are not really atomic probably breaks things.  However implementing
@@ -5149,7 +5210,9 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
             goto efault;
         ret = get_errno(stat(path(p), &st));
         unlock_user(p, arg1, 0);
-        goto do_stat64;
+	if (!is_error(ret))
+		ret = host_to_target_stat64(cpu_env, arg2, &st);
+	break;
 #endif
 #ifdef TARGET_NR_lstat64
     case TARGET_NR_lstat64:
@@ -5157,67 +5220,24 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
             goto efault;
         ret = get_errno(lstat(path(p), &st));
         unlock_user(p, arg1, 0);
-        goto do_stat64;
+	if (!is_error(ret))
+		ret = host_to_target_stat64(cpu_env, arg2, &st);
+	break;
 #endif
 #ifdef TARGET_NR_fstat64
     case TARGET_NR_fstat64:
-        {
-            ret = get_errno(fstat(arg1, &st));
-        do_stat64:
-            if (!is_error(ret)) {
-#ifdef TARGET_ARM
-                if (((CPUARMState *)cpu_env)->eabi) {
-                    struct target_eabi_stat64 *target_st;
-
-                    if (!lock_user_struct(VERIFY_WRITE, target_st, arg2, 0))
-                        goto efault;
-                    memset(target_st, 0, sizeof(struct target_eabi_stat64));
-                    __put_user(st.st_dev, &target_st->st_dev);
-                    __put_user(st.st_ino, &target_st->st_ino);
-#ifdef TARGET_STAT64_HAS_BROKEN_ST_INO
-                    __put_user(st.st_ino, &target_st->__st_ino);
-#endif
-                    __put_user(st.st_mode, &target_st->st_mode);
-                    __put_user(st.st_nlink, &target_st->st_nlink);
-                    __put_user(st.st_uid, &target_st->st_uid);
-                    __put_user(st.st_gid, &target_st->st_gid);
-                    __put_user(st.st_rdev, &target_st->st_rdev);
-                    __put_user(st.st_size, &target_st->st_size);
-                    __put_user(st.st_blksize, &target_st->st_blksize);
-                    __put_user(st.st_blocks, &target_st->st_blocks);
-                    __put_user(st.st_atime, &target_st->target_st_atime);
-                    __put_user(st.st_mtime, &target_st->target_st_mtime);
-                    __put_user(st.st_ctime, &target_st->target_st_ctime);
-                    unlock_user_struct(target_st, arg2, 1);
-                } else
+	ret = get_errno(fstat(arg1, &st));
+	if (!is_error(ret))
+		ret = host_to_target_stat64(cpu_env, arg2, &st);
+        break;
 #endif
-                {
-                    struct target_stat64 *target_st;
-
-                    if (!lock_user_struct(VERIFY_WRITE, target_st, arg2, 0))
-                        goto efault;
-                    memset(target_st, 0, sizeof(struct target_stat64));
-                    __put_user(st.st_dev, &target_st->st_dev);
-                    __put_user(st.st_ino, &target_st->st_ino);
-#ifdef TARGET_STAT64_HAS_BROKEN_ST_INO
-                    __put_user(st.st_ino, &target_st->__st_ino);
-#endif
-                    __put_user(st.st_mode, &target_st->st_mode);
-                    __put_user(st.st_nlink, &target_st->st_nlink);
-                    __put_user(st.st_uid, &target_st->st_uid);
-                    __put_user(st.st_gid, &target_st->st_gid);
-                    __put_user(st.st_rdev, &target_st->st_rdev);
-                    /* XXX: better use of kernel struct */
-                    __put_user(st.st_size, &target_st->st_size);
-                    __put_user(st.st_blksize, &target_st->st_blksize);
-                    __put_user(st.st_blocks, &target_st->st_blocks);
-                    __put_user(st.st_atime, &target_st->target_st_atime);
-                    __put_user(st.st_mtime, &target_st->target_st_mtime);
-                    __put_user(st.st_ctime, &target_st->target_st_ctime);
-                    unlock_user_struct(target_st, arg2, 1);
-                }
-            }
-        }
+#ifdef TARGET_NR_fstatat64
+    case TARGET_NR_fstatat64:
+        if (!(p = lock_user_string(arg2)))
+            goto efault;
+	ret = get_errno(fstatat(arg1, p, &st, arg4));
+	if (!is_error(ret))
+		ret = host_to_target_stat64(cpu_env, arg3, &st);
         break;
 #endif
 #ifdef USE_UID16
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Implement futimesat() syscall

[Kirill A. Shutemov]

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |   20 ++++++++++++++++++++
 1 files changed, 20 insertions(+), 0 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 863e319..faf0003 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -3656,6 +3656,26 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
             unlock_user(p, arg1, 0);
         }
         break;
+#ifdef TARGET_NR_futimesat
+    case TARGET_NR_futimesat:
+        {
+            struct timeval *tvp, tv[2];
+            if (arg3) {
+                if (copy_from_user_timeval(&tv[0], arg3)
+                    || copy_from_user_timeval(&tv[1],
+                                              arg3 + sizeof(struct target_timeval)))
+                    goto efault;
+                tvp = tv;
+            } else {
+                tvp = NULL;
+            }
+            if (!(p = lock_user_string(arg2)))
+                goto efault;
+            ret = get_errno(futimesat(arg1, p, tvp));
+            unlock_user(p, arg2, 0);
+        }
+        break;
+#endif
 #ifdef TARGET_NR_stty
     case TARGET_NR_stty:
         goto unimplemented;
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Imaplement ioctls MTIOCTOP, MTIOCGET and MTIOCPOS

[Kirill A. Shutemov]

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/ioctls.h        |    4 ++++
 linux-user/syscall.c       |    1 +
 linux-user/syscall_defs.h  |    4 ++++
 linux-user/syscall_types.h |    6 ++++++
 4 files changed, 15 insertions(+), 0 deletions(-)

diff --git a/linux-user/ioctls.h b/linux-user/ioctls.h
index c1ca2d5..685cc71 100644
--- a/linux-user/ioctls.h
+++ b/linux-user/ioctls.h
@@ -310,3 +310,7 @@
   IOCTL(LOOP_GET_STATUS64, IOC_W, MK_PTR(MK_STRUCT(STRUCT_loop_info64)))
 #endif
   IOCTL(LOOP_CHANGE_FD, 0, TYPE_INT)
+
+  IOCTL(MTIOCTOP, IOC_W, MK_PTR(MK_STRUCT(STRUCT_mtop)))
+  IOCTL(MTIOCGET, IOC_R, MK_PTR(MK_STRUCT(STRUCT_mtget)))
+  IOCTL(MTIOCPOS, IOC_R, MK_PTR(MK_STRUCT(STRUCT_mtpos)))
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index faf0003..5810d65 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -69,6 +69,7 @@
 #include <linux/soundcard.h>
 #include <linux/dirent.h>
 #include <linux/kd.h>
+#include <linux/mtio.h>
 #include "linux_loop.h"
 
 #include "qemu.h"
diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h
index 52242b6..9896522 100644
--- a/linux-user/syscall_defs.h
+++ b/linux-user/syscall_defs.h
@@ -1923,6 +1923,10 @@ struct target_eabi_flock64 {
 #define TARGET_VFAT_IOCTL_READDIR_BOTH    TARGET_IORU('r', 1)
 #define TARGET_VFAT_IOCTL_READDIR_SHORT   TARGET_IORU('r', 2)
 
+#define TARGET_MTIOCTOP        TARGET_IOW('m', 1, struct mtop)
+#define TARGET_MTIOCGET        TARGET_IOR('m', 2, struct mtget)
+#define TARGET_MTIOCPOS        TARGET_IOR('m', 3, struct mtpos)
+
 struct target_sysinfo {
     abi_long uptime;                /* Seconds since boot */
     abi_ulong loads[3];             /* 1, 5, and 15 minute load averages */
diff --git a/linux-user/syscall_types.h b/linux-user/syscall_types.h
index bb4fb4e..283d32d 100644
--- a/linux-user/syscall_types.h
+++ b/linux-user/syscall_types.h
@@ -108,3 +108,9 @@ STRUCT(loop_info64,
        MK_ARRAY(TYPE_CHAR, 64),  /* lo_crypt_name */
        MK_ARRAY(TYPE_CHAR, 32),  /* lo_encrypt_key */
        MK_ARRAY(TYPE_ULONGLONG, 2))  /* lo_init */
+
+
+STRUCT(mtop, TYPE_SHORT, TYPE_INT)
+STRUCT(mtget, TYPE_LONG, TYPE_LONG, TYPE_LONG, TYPE_LONG, TYPE_LONG,
+       TYPE_INT, TYPE_INT)
+STRUCT(mtpos, TYPE_LONG)
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Introduce option -binfmt-misc-friendly

[Kirill A. Shutemov]

-binfmt-misc-friendly makes qemu compatible with binfmt_misc's flags 'P'
and 'O'.

'P' - preserve-argv[0].  Legacy behavior of binfmt_misc is to overwrite the
      original argv[0] with the full path to the binary.  When this flag is
      included, binfmt_misc will add an argument to the argument vector for
      this purpose, thus preserving the original argv[0].

'O' - open-binary. Legacy behavior of binfmt_misc is to pass the full path
      of the binary to the interpreter as an argument. When this flag is
      included, binfmt_misc will open the file for reading and pass its
      descriptor as an argument, instead of the full path, thus allowing
      the interpreter to execute non-readable binaries.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/linuxload.c |    7 +----
 linux-user/main.c      |   54 ++++++++++++++++++++++++++++++++++++++++-------
 linux-user/qemu.h      |    2 +-
 3 files changed, 49 insertions(+), 14 deletions(-)

diff --git a/linux-user/linuxload.c b/linux-user/linuxload.c
index ada7c69..cbd90f7 100644
--- a/linux-user/linuxload.c
+++ b/linux-user/linuxload.c
@@ -154,7 +154,7 @@ abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp,
     return sp;
 }
 
-int loader_exec(const char * filename, char ** argv, char ** envp,
+int loader_exec(int fd, const char * filename, char ** argv, char ** envp,
              struct target_pt_regs * regs, struct image_info *infop)
 {
     struct linux_binprm bprm;
@@ -164,10 +164,7 @@ int loader_exec(const char * filename, char ** argv, char ** envp,
     bprm.p = TARGET_PAGE_SIZE*MAX_ARG_PAGES-sizeof(unsigned int);
     for (i=0 ; i<MAX_ARG_PAGES ; i++)       /* clear page-table */
             bprm.page[i] = 0;
-    retval = open(filename, O_RDONLY);
-    if (retval < 0)
-        return retval;
-    bprm.fd = retval;
+    bprm.fd = fd;
     bprm.filename = (char *)filename;
     bprm.argc = count(argv);
     bprm.argv = argv;
diff --git a/linux-user/main.c b/linux-user/main.c
index 4bf739e..d3223f2 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -26,6 +26,7 @@
 
 #include "qemu.h"
 #include "qemu-common.h"
+#include "elf.h"
 /* For tb_lock */
 #include "exec-all.h"
 
@@ -2180,12 +2181,13 @@ static void usage(void)
            "Linux CPU emulator (compiled for %s emulation)\n"
            "\n"
            "Standard options:\n"
-           "-h                print this help\n"
-           "-g port           wait gdb connection to port\n"
-           "-L path           set the elf interpreter prefix (default=%s)\n"
-           "-s size           set the stack size in bytes (default=%ld)\n"
-           "-cpu model        select CPU (-cpu ? for list)\n"
-           "-drop-ld-preload  drop LD_PRELOAD for target process\n"
+           "-h                     print this help\n"
+           "-g port                wait gdb connection to port\n"
+           "-L path                set the elf interpreter prefix (default=%s)\n"
+           "-s size                set the stack size in bytes (default=%ld)\n"
+           "-cpu model             select CPU (-cpu ? for list)\n"
+           "-drop-ld-preload       drop LD_PRELOAD for target process\n"
+           "-binfmt-misc-friendly  make qemu compatible with binfmt_misc's flags 'O' and 'P' \n"
            "\n"
            "Debug options:\n"
            "-d options   activate log (logfile=%s)\n"
@@ -2218,9 +2220,10 @@ void init_task_state(TaskState *ts)
     ts->sigqueue_table[i].next = NULL;
 }
  
-int main(int argc, char **argv)
+int main(int argc, char **argv, char **envp)
 {
     const char *filename;
+    int fd = -1;
     const char *cpu_model;
     struct target_pt_regs regs1, *regs = &regs1;
     struct image_info info1, *info = &info1;
@@ -2230,6 +2233,7 @@ int main(int argc, char **argv)
     const char *r;
     int gdbstub_port = 0;
     int drop_ld_preload = 0, environ_count = 0;
+    int binfmt_misc_friendly = 0;
     char **target_environ, **wrk, **dst;
 
     if (argc <= 1)
@@ -2302,6 +2306,8 @@ int main(int argc, char **argv)
             drop_ld_preload = 1;
         } else if (!strcmp(r, "strace")) {
             do_strace = 1;
+        } else if (!strcmp(r, "binfmt-misc-friendly")) {
+	    binfmt_misc_friendly = 1;
         } else
         {
             usage();
@@ -2381,7 +2387,39 @@ int main(int argc, char **argv)
     }
     *dst = NULL; /* NULL terminate target_environ */
 
-    if (loader_exec(filename, argv+optind, target_environ, regs, info) != 0) {
+    if (binfmt_misc_friendly) {
+#if HOST_LONG_BITS == 32
+#define Elf_Dyn Elf32_Dyn
+#else
+#define Elf_Dyn Elf64_Dyn
+#endif
+	Elf_Dyn *auxv;
+
+	optind++; /* Handle binfmt_misc's option 'P' */
+
+	/* Handle binfmt_misc's option 'O' */
+	while(*envp++ != NULL); /* skip envp. we are on auxv now */
+	for(auxv = (Elf_Dyn *)envp; auxv->d_tag != AT_NULL; auxv++) {
+	    if( auxv->d_tag == AT_EXECFD) {
+		fd = auxv->d_un.d_val;
+		break;
+	    }
+	}
+
+	if (fd < 0) {
+	    printf("Cannot find binary file descriptor\n");
+	    _exit(1);
+	}
+
+    } else {
+	fd = open(filename, O_RDONLY);
+	if (fd < 0) {
+	    printf("Cannot open file %s: %s\n", filename, strerror(errno));
+	    _exit(1);
+	}
+    }
+
+    if (loader_exec(fd, filename, argv+optind, target_environ, regs, info) != 0) {
         printf("Error loading %s\n", filename);
         _exit(1);
     }
diff --git a/linux-user/qemu.h b/linux-user/qemu.h
index a12cc9b..216e2f8 100644
--- a/linux-user/qemu.h
+++ b/linux-user/qemu.h
@@ -168,7 +168,7 @@ struct linux_binprm {
 void do_init_thread(struct target_pt_regs *regs, struct image_info *infop);
 abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp,
                               abi_ulong stringp, int push_ptr);
-int loader_exec(const char * filename, char ** argv, char ** envp,
+int loader_exec(int fd, const char * filename, char ** argv, char ** envp,
              struct target_pt_regs * regs, struct image_info *infop);
 
 int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs,
-- 
1.5.6.5.GIT

[Qemu-devel] Linux user emulator maintainer

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 523 bytes --]

Linux user emulator doesn't have active maintainer. Nobody reviews patches
to linux-user. It's very sad :( 

I'm porting ALT Linux Sisyphus to the ARM architecture using qemu-arm. I'm
very interested in properly work of Linux user emulator. I have series of
patches ready for upstream and I can prepare some patches shortly (including
some IPC improvements).

If you will allow, I can perform maintenance duties.

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

[Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

vfork() is a kind of fork, not thread despite CLONE_VM

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 56b4138..124d14e 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -2788,7 +2788,7 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
     sigset_t sigmask;
 #endif
 
-    if (flags & CLONE_VM) {
+    if (!(flags & CLONE_VFORK) && (flags & CLONE_VM)) {
 #if defined(USE_NPTL)
         new_thread_info info;
         pthread_attr_t attr;
@@ -2857,8 +2857,8 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
 #endif
 #endif
     } else {
-        /* if no CLONE_VM, we consider it is a fork */
-        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2)) != 0)
+        /* we consider it is a fork or vfork */
+        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2 | CLONE_VFORK | CLONE_VM)) != 0)
             return -EINVAL;
         fork_start();
         ret = fork();
-- 
1.5.6.5.GIT

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[andrzej zaborowski]

2008/9/18 Kirill A. Shutemov <kirill@shutemov.name>:
> vfork() is a kind of fork, not thread despite CLONE_VM

According to clone(2) it can be either, the only difference is that
vfork() suspends the parent process.  So if CLONE_VM is set, I think
still the pthread / clone way should be used and the child thread
should be waited on.

On the other hand the patch makes fork() and vfork() be treated identically?

Cheers

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 1106 bytes --]

On Sat, Sep 20, 2008 at 04:56:45AM +0200, andrzej zaborowski wrote:
> 2008/9/18 Kirill A. Shutemov <kirill@shutemov.name>:
> > vfork() is a kind of fork, not thread despite CLONE_VM
> 
> According to clone(2) it can be either, the only difference is that
> vfork() suspends the parent process.  So if CLONE_VM is set, I think
> still the pthread / clone way should be used and the child thread
> should be waited on.

vfork() suspends the parent process until a call of execve(2) or _exit(2).
If child call execnv(2) it replaces whole process, not only the thread.
If child call _exit(2) it stops while process, not only the thread.

> On the other hand the patch makes fork() and vfork() be treated identically?

$ cat usr/klibc/vfork.c
/*
 * vfork.c
 *
 * Emulate vfork() with fork() if necessary
 */

#include <unistd.h>
#include <klibc/compiler.h>
#include <klibc/sysconfig.h>

#if !_KLIBC_NO_MMU && !_KLIBC_REAL_VFORK
int vfork(void)
{
        return fork();
}
#endif

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[andrzej zaborowski]

2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> On Sat, Sep 20, 2008 at 04:56:45AM +0200, andrzej zaborowski wrote:
>> 2008/9/18 Kirill A. Shutemov <kirill@shutemov.name>:
>> > vfork() is a kind of fork, not thread despite CLONE_VM
>>
>> According to clone(2) it can be either, the only difference is that
>> vfork() suspends the parent process.  So if CLONE_VM is set, I think
>> still the pthread / clone way should be used and the child thread
>> should be waited on.
>
> vfork() suspends the parent process until a call of execve(2) or _exit(2).
> If child call execnv(2) it replaces whole process, not only the thread.
> If child call _exit(2) it stops while process, not only the thread.

Do you mean that's the current behavior in qemu?  That's not what clone(2) says.

>
>> On the other hand the patch makes fork() and vfork() be treated identically?
>
> $ cat usr/klibc/vfork.c
> /*
>  * vfork.c
>  *
>  * Emulate vfork() with fork() if necessary
>  */
>
> #include <unistd.h>
> #include <klibc/compiler.h>
> #include <klibc/sysconfig.h>
>
> #if !_KLIBC_NO_MMU && !_KLIBC_REAL_VFORK
> int vfork(void)
> {
>        return fork();
> }
> #endif

Well, that's libc. clone with CLONE_VFORK and without it are still not
the same thing.  CLONE_VM and CLONE_VFORK are ortogonal to one
another, not the opposite of.

Cheers

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 2249 bytes --]

On Sat, Sep 20, 2008 at 02:45:57PM +0200, andrzej zaborowski wrote:
> 2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> > On Sat, Sep 20, 2008 at 04:56:45AM +0200, andrzej zaborowski wrote:
> >> 2008/9/18 Kirill A. Shutemov <kirill@shutemov.name>:
> >> > vfork() is a kind of fork, not thread despite CLONE_VM
> >>
> >> According to clone(2) it can be either, the only difference is that
> >> vfork() suspends the parent process.  So if CLONE_VM is set, I think
> >> still the pthread / clone way should be used and the child thread
> >> should be waited on.
> >
> > vfork() suspends the parent process until a call of execve(2) or _exit(2).
> > If child call execnv(2) it replaces whole process, not only the thread.
> > If child call _exit(2) it stops while process, not only the thread.
> 
> Do you mean that's the current behavior in qemu?  That's not what clone(2) says.

Currently, qemu with NPTL(I've tested on ARM EABI) on CLONE_VM create
thread using pthread interface. Every thread has its own stack.

vfork() is clone() with flags CLONE_VM and CLONE_VFORK. 

man vfork(2):

   Linux Description
       vfork(),  just  like  fork(2), creates a child process of the calling
       process.  For details and return value and errors, see fork(2).

       vfork() is a special case of clone(2).  It is used to create new pro-
       cesses without copying the page tables of the parent process.  It may
       be useful in performance sensitive applications where a child will be
       created which then immediately issues an execve(2).

       vfork()  differs  from  fork(2) in that the parent is suspended until
       the child makes a call to execve(2) or _exit(2).   The  child  shares
       all  memory  with its parent, including the stack, until execve(2) is
       issued by the child.  The child must  not  return  from  the  current
       function or call exit(3), but may call _exit(2).

       Signal handlers are inherited, but not shared.  Signals to the parent
       arrive after the child releases the parent's memory.

So, implementation vfork() using pthread is wrong.

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[andrzej zaborowski]

2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> So, implementation vfork() using pthread is wrong.

Agreed, but implementation of vfork() using fork() is wrong, too. If
we allow a hack, it should be commented, the second thing that needs
to be commented is why the value of CLONE_VM flag is ignored if
CLONE_VFORK is set -- on Linux it's not ignored.

Cheers

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 1364 bytes --]

On Sat, Sep 20, 2008 at 03:52:55PM +0200, andrzej zaborowski wrote:
> 2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> > So, implementation vfork() using pthread is wrong.
> 
> Agreed, but implementation of vfork() using fork() is wrong, too.

Why? 

man 2 vfork():

BUGS
       It  is  rather  unfortunate  that Linux revived this specter from the
       past.  The BSD man page states: "This system call will be  eliminated
       when  proper system sharing mechanisms are implemented.  Users should
       not depend on the memory sharing semantics of vfork() as it will,  in
       that case, be made synonymous to fork(2)."

If any program doesn't work with vfork() implemented using fork(). it's 
program bug.


> If
> we allow a hack, it should be commented, the second thing that needs
> to be commented is why the value of CLONE_VM flag is ignored if
> CLONE_VFORK is set -- on Linux it's not ignored.

vfork() is a hack itself. It was introduced when fork() was very expensive.
Linux fork() is implemented using copy-on-write pages, so the only penalty 
incurred by fork() is the time and memory required to duplicate the parent's
page tables. It's quite cheap. So I think emulate vfork() using fork() is 
correct.

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[andrzej zaborowski]

2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> On Sat, Sep 20, 2008 at 03:52:55PM +0200, andrzej zaborowski wrote:
>> 2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
>> > So, implementation vfork() using pthread is wrong.
>>
>> Agreed, but implementation of vfork() using fork() is wrong, too.
>
> Why?
>
> man 2 vfork():
>
> BUGS
>       It  is  rather  unfortunate  that Linux revived this specter from the
>       past.  The BSD man page states: "This system call will be  eliminated
>       when  proper system sharing mechanisms are implemented.  Users should
>       not depend on the memory sharing semantics of vfork() as it will,  in
>       that case, be made synonymous to fork(2)."
>
> If any program doesn't work with vfork() implemented using fork(). it's
> program bug.
>
>
>> If
>> we allow a hack, it should be commented, the second thing that needs
>> to be commented is why the value of CLONE_VM flag is ignored if
>> CLONE_VFORK is set -- on Linux it's not ignored.
>
> vfork() is a hack itself. It was introduced when fork() was very expensive.

Ok, perhaps I'm nit picking.  clone(2) specifies some semantics for
CLONE_VFORK regardless of the purpose and this implementation is
nowhere near these semantics.  I'll just add the same comment that
klibc has and push the patch.

Cheers

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 1590 bytes --]

On Sat, Sep 20, 2008 at 04:35:25PM +0200, andrzej zaborowski wrote:
> 2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> > On Sat, Sep 20, 2008 at 03:52:55PM +0200, andrzej zaborowski wrote:
> >> 2008/9/20 Kirill A. Shutemov <kirill@shutemov.name>:
> >> > So, implementation vfork() using pthread is wrong.
> >>
> >> Agreed, but implementation of vfork() using fork() is wrong, too.
> >
> > Why?
> >
> > man 2 vfork():
> >
> > BUGS
> >       It  is  rather  unfortunate  that Linux revived this specter from the
> >       past.  The BSD man page states: "This system call will be  eliminated
> >       when  proper system sharing mechanisms are implemented.  Users should
> >       not depend on the memory sharing semantics of vfork() as it will,  in
> >       that case, be made synonymous to fork(2)."
> >
> > If any program doesn't work with vfork() implemented using fork(). it's
> > program bug.
> >
> >
> >> If
> >> we allow a hack, it should be commented, the second thing that needs
> >> to be commented is why the value of CLONE_VM flag is ignored if
> >> CLONE_VFORK is set -- on Linux it's not ignored.
> >
> > vfork() is a hack itself. It was introduced when fork() was very expensive.
> 
> Ok, perhaps I'm nit picking.  clone(2) specifies some semantics for
> CLONE_VFORK regardless of the purpose and this implementation is
> nowhere near these semantics.  I'll just add the same comment that
> klibc has and push the patch.

Thanks!

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 622 bytes --]

On Sat, Sep 20, 2008 at 04:56:45AM +0200, andrzej zaborowski wrote:
> 2008/9/18 Kirill A. Shutemov <kirill@shutemov.name>:
> > vfork() is a kind of fork, not thread despite CLONE_VM
> 
> According to clone(2) it can be either, the only difference is that
> vfork() suspends the parent process.  So if CLONE_VM is set, I think
> still the pthread / clone way should be used and the child thread
> should be waited on.

Also process created with vfork(2) share stack with parent. Every thread
has its own stack.

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]

[Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

vfork() is a kind of fork, not thread despite CLONE_VM

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index fd4890e..8a00734 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -2787,7 +2787,7 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
     sigset_t sigmask;
 #endif
 
-    if (flags & CLONE_VM) {
+    if (!(flags & CLONE_VFORK) && (flags & CLONE_VM)) {
 #if defined(USE_NPTL)
         new_thread_info info;
         pthread_attr_t attr;
@@ -2856,8 +2856,8 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
 #endif
 #endif
     } else {
-        /* if no CLONE_VM, we consider it is a fork */
-        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2)) != 0)
+        /* we consider it is a fork or vfork */
+        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2 | CLONE_VFORK | CLONE_VM)) != 0)
             return -EINVAL;
         fork_start();
         ret = fork();
-- 
1.5.6.5.GIT

[Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

vfork() is a kind of fork, not thread despite CLONE_VM

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
---
 linux-user/syscall.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index fd4890e..2abdc83 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -2787,7 +2787,7 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
     sigset_t sigmask;
 #endif
 
-    if (flags & CLONE_VM) {
+    if (!(flags & CLONE_VFORK) && flags & CLONE_VM) {
 #if defined(USE_NPTL)
         new_thread_info info;
         pthread_attr_t attr;
@@ -2856,8 +2856,8 @@ static int do_fork(CPUState *env, unsigned int flags, abi_ulong newsp,
 #endif
 #endif
     } else {
-        /* if no CLONE_VM, we consider it is a fork */
-        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2)) != 0)
+        /* we consider it is a fork or vfork */
+        if ((flags & ~(CSIGNAL | CLONE_NPTL_FLAGS2 | CLONE_VFORK | CLONE_VM)) != 0)
             return -EINVAL;
         fork_start();
         ret = fork();
-- 
1.5.6.5.GIT

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Jamie Lokier]

Kirill A. Shutemov wrote:
> -    if (flags & CLONE_VM) {
> +    if (!(flags & CLONE_VFORK) && flags & CLONE_VM) {

Parentheses around (flags & CLONE_VM) would be good here.

-- Jamie

Re: [Qemu-devel] [PATCH] Fix vfork() syscall emulation

[Kirill A. Shutemov]

[-- Attachment #1: Type: text/plain, Size: 387 bytes --]

On Sun, Aug 24, 2008 at 03:47:33PM +0100, Jamie Lokier wrote:
> Kirill A. Shutemov wrote:
> > -    if (flags & CLONE_VM) {
> > +    if (!(flags & CLONE_VFORK) && flags & CLONE_VM) {
> 
> Parentheses around (flags & CLONE_VM) would be good here.

Agreed. I'll resend patch soon.

-- 
Regards,  Kirill A. Shutemov
 + Belarus, Minsk
 + ALT Linux Team, http://www.altlinux.com/

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 197 bytes --]